ComfyUi 0.3.29 positive node fix,
Perfil de execução
Descrição da fonte
✨ WAN2.1 — Image to video — Simple Workflow
A clean, all-in-one WAN image-to-video workflow built entirely with the UmeAiRT Toolkit for ComfyUI. Only 12 nodes . No spaghetti wires. Just load your model, write your prompt, and hit generate.
⚠️ IMPORTANT — Nodes 2.0 Required
This workflow is built for the Nodes 2.0 (Vue) interface of ComfyUI. If you don't enable it, the workflow may have display problems.
How to activate Nodes 2.0:
Open ComfyUI
Go to Settings (⚙️ icon, bottom-left)
Comentário gerado por IA
Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são claramente identificadas.
Use this ComfyUI workflow with Wan Video to turn an input image and written prompt into video; it also supports text-to-video, optional SeedVR2 tiled upscaling, and saving generated images with all generation parameters.
Choose the auto or manual setup path: the auto version lists automatic model downloads, while manual setup lists model files and their ComfyUI folders.
Manual setup lists an image and written prompt, plus an I2V model, CLIP, CLIP-VISION, VAE, Speed LoRA, and an upscaling model.
The base option lists 480p or 720p I2V models; GGUF options list Q8, Q5, or Q3 at 480p or 720p.
Generated images can retain all generation parameters for online publishing and remixing.
Before loading it, turn on “Use Nodes V2 (Vue)” in ComfyUI Settings and refresh the page.
Sugestão · não verificado
Install ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.
Sugestão · não verificado
Named node packs include: comfyui-custom-scripts, comfyui-easy-use, comfyui-florence2, comfyui-frame-interpolation, comfyui-impact-pack, comfyui-kjnodes, comfyui-multigpu, comfyui-mxtoolkit, comfyui-videohelpersuite, ComfyUI-Upscaler-Tensorrt, rgthree-comfy, and was-node-suite.-S
Named model items include: clip_vision_h.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, wan2.1_i2v_480p_14B_bf16.safetensors, wan2.1-i2v-14b-480p-Q5_K_M.gguf, rife47.pth, and MiaoshouAI/Florence-2-base-PromptGen-v2.0.
ComfyUI-UmeAiRT-Toolkit is listed as the custom node, with the upscaler, face detailer, and metadata saver packaged internally; no other custom nodes are listed as needed.
Toggle the built-in SeedVR2 tiled upscaler on or off; the description notes that it is slower than a classic upscaler and offers significantly better quality.
Use three LoRA slots with individual on/off toggles and strength controls; additional LoRA modules can be connected.
The package list names additional node packs, but it does not show which ones this workflow needs; verify the required packages before running.
Sugestão · não verificado
No license is listed; check the applicable usage terms before publishing.
Sugestão · não verificado
Isso precisa ser editado?
Faça login para enviar uma solicitação de edição.
Fontes
1 fonteTrechos de fonte
2 trechosSource context: 101452 downloads · Type Workflows · Base model Wan Video
Find "Use Nodes V2 (Vue)" and toggle it ON
Refresh the page
Load the workflow
If you prefer the classic interface, check out my Legacy version of this workflow instead ( link ).
🎯 Features
Text-to-video generation
Automatic download of models in auto version
Built-in SeedVR2 upscaler — high-quality tiled upscaling (toggleable on/off) Slower than a classic upscaler, but significantly better quality
Full metadata embedding — your images are saved with all generation parameters, ready for online publishing and remixing
3 LoRA slots — with individual on/off toggles and strength control and you can connect as many other lora modules to each other for as many LoRA as you want.
📦 Custom Node Required
Only one custom node to install:
👉 ComfyUI-UmeAiRT-Toolkit
Install via ComfyUI Manager (search "UmeAiRT") or use the UmeAiRT Auto-Installer . The Toolkit packages everything internally — upscaler, face detailer, metadata saver. No other custom nodes needed.
📂 Files you need (in manual version)
For base version I2V Model : 480p or 720p In models/diffusion_models
For GGUF version I2V Quant Model :
Common files : CLIP: umt5_xxl_fp8_e4m3fn_scaled.safetensors in models/clip CLIP-VISION: clip_vision_h.safetensors in models/clip_vision VAE: wan_2.1_vae.safetensors in models/vae Speed LoRA: 480p , 720p in models/loras
ANY upscale model:
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in models/upscale_models
Estimativa de requisito VRAM
Estimativa indisponível
38,2 GB distribuídos em 4 de 6 arquivos de modelo. Total de arquivos do modelo + 25% de overhead de carregamento + 2 GB de buffer de execução, arredondado para cima.
Requisitos
Requisitos 18Vision model · 1.18 GB · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
MiaoshouAI/Florence-2-base-PromptGen-v2.0
Arquivo não verificadoVision model · Hugging Face · MiaoshouAI/Florence-2-base-PromptGen-v2.0 · Florence 2 Base PromptGen v2.0
Checkpoint · Hugging Face
umt5_xxl_fp8_e4m3fn_scaled.safetensors
EncontradoText encoder · 6.27 GB · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · 242 MB · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
wan2.1_i2v_480p_14B_bf16.safetensors
EncontradoCheckpoint · 30.5 GB · SAFETENSORS · Hugging Face · dx158/wan_2.1_comfyui_repackaged
Pacote de nós · Registry
Pacote de nós · Registry
comfyui-florence2
Source context: 100949 downloads · Type Workflows · Base model Wan Video
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
was-node-suite-comfyui
PossívelPacote de nós · Registry